Sciweavers

134 search results - page 12 / 27
» On the Complexity of Approximating the VC Dimension
Sort
View
STOC
2006
ACM
244views Algorithms» more  STOC 2006»
15 years 12 months ago
Approximate nearest neighbors and the fast Johnson-Lindenstrauss transform
We introduce a new low-distortion embedding of d 2 into O(log n) p (p = 1, 2), called the Fast-Johnson-LindenstraussTransform. The FJLT is faster than standard random projections ...
Nir Ailon, Bernard Chazelle
81
Voted
ICML
2004
IEEE
16 years 14 days ago
SVM-based generalized multiple-instance learning via approximate box counting
The multiple-instance learning (MIL) model has been very successful in application areas such as drug discovery and content-based imageretrieval. Recently, a generalization of thi...
Qingping Tao, Stephen D. Scott, N. V. Vinodchandra...
88
Voted
JSCIC
2007
89views more  JSCIC 2007»
14 years 11 months ago
Adjoint Recovery of Superconvergent Linear Functionals from Galerkin Approximations. The One-dimensional Case
In this paper, we extend the adjoint error correction of Pierce and Giles [SIAM Review, 42 (2000), pp. 247-264] for obtaining superconvergent approximations of functionals to Gale...
Bernardo Cockburn, Ryuhei Ichikawa
ISCI
2000
84views more  ISCI 2000»
14 years 11 months ago
Automating the approximate record-matching process
Data Quality has many dimensions one of which is accuracy. Accuracy is usually compromised by errors accidentally or intensionally introduced in a database system. These errors re...
Vassilios S. Verykios, Ahmed K. Elmagarmid, Elias ...
ALT
2006
Springer
15 years 8 months ago
How Many Query Superpositions Are Needed to Learn?
Abstract. This paper introduces a framework for quantum exact learning via queries, the so-called quantum protocol. It is shown that usual protocols in the classical learning setti...
Jorge Castro